From Insights to Actions: The Impact of Interpretability and Analysis Research on NLP
- URL: http://arxiv.org/abs/2406.12618v1
- Date: Tue, 18 Jun 2024 13:45:07 GMT
- Title: From Insights to Actions: The Impact of Interpretability and Analysis Research on NLP
- Authors: Marius Mosbach, Vagrant Gautam, Tomás Vergara-Browne, Dietrich Klakow, Mor Geva,
- Abstract summary: Interpretability and analysis (IA) research is a growing subfield within NLP.
We seek to quantify the impact of IA research on the broader field of NLP.
- Score: 28.942812379900673
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Interpretability and analysis (IA) research is a growing subfield within NLP with the goal of developing a deeper understanding of the behavior or inner workings of NLP systems and methods. Despite growing interest in the subfield, a commonly voiced criticism is that it lacks actionable insights and therefore has little impact on NLP. In this paper, we seek to quantify the impact of IA research on the broader field of NLP. We approach this with a mixed-methods analysis of: (1) a citation graph of 185K+ papers built from all papers published at ACL and EMNLP conferences from 2018 to 2023, and (2) a survey of 138 members of the NLP community. Our quantitative results show that IA work is well-cited outside of IA, and central in the NLP citation graph. Through qualitative analysis of survey responses and manual annotation of 556 papers, we find that NLP researchers build on findings from IA work and perceive it is important for progress in NLP, multiple subfields, and rely on its findings and terminology for their own work. Many novel methods are proposed based on IA findings and highly influenced by them, but highly influential non-IA work cites IA findings without being driven by them. We end by summarizing what is missing in IA work today and provide a call to action, to pave the way for a more impactful future of IA research.
Related papers
- Shoulders of Giants: A Look at the Degree and Utility of Openness in NLP Research [1.1650821883155187]
We observe that papers published in different NLP venues show different patterns related to artefact reuse.
More than 30% of the papers we analysed do not release their artefacts publicly, despite promising to do so.
We observe a wide language-wise disparity in publicly available NLP-related artefacts.
arXiv Detail & Related papers (2024-06-10T04:47:27Z) - What Can Natural Language Processing Do for Peer Review? [173.8912784451817]
In modern science, peer review is widely used, yet it is hard, time-consuming, and prone to error.
Since the artifacts involved in peer review are largely text-based, Natural Language Processing has great potential to improve reviewing.
We detail each step of the process from manuscript submission to camera-ready revision, and discuss the associated challenges and opportunities for NLP assistance.
arXiv Detail & Related papers (2024-05-10T16:06:43Z) - Responsible AI Considerations in Text Summarization Research: A Review
of Current Practices [89.85174013619883]
We focus on text summarization, a common NLP task largely overlooked by the responsible AI community.
We conduct a multi-round qualitative analysis of 333 summarization papers from the ACL Anthology published between 2020-2022.
We focus on how, which, and when responsible AI issues are covered, which relevant stakeholders are considered, and mismatches between stated and realized research goals.
arXiv Detail & Related papers (2023-11-18T15:35:36Z) - Exploring the Landscape of Natural Language Processing Research [3.3916160303055567]
Several NLP-related approaches have been surveyed in the research community.
A comprehensive study that categorizes established topics, identifies trends, and outlines areas for future research remains absent.
As a result, we present a structured overview of the research landscape, provide a taxonomy of fields of study in NLP, analyze recent developments in NLP, summarize our findings, and highlight directions for future work.
arXiv Detail & Related papers (2023-07-20T07:33:30Z) - Surveying (Dis)Parities and Concerns of Compute Hungry NLP Research [75.84463664853125]
We provide a first attempt to quantify concerns regarding three topics, namely, environmental impact, equity, and impact on peer reviewing.
We capture existing (dis)parities between different and within groups with respect to seniority, academia, and industry.
We devise recommendations to mitigate found disparities, some of which already successfully implemented.
arXiv Detail & Related papers (2023-06-29T12:44:53Z) - NLPeer: A Unified Resource for the Computational Study of Peer Review [58.71736531356398]
We introduce NLPeer -- the first ethically sourced multidomain corpus of more than 5k papers and 11k review reports from five different venues.
We augment previous peer review datasets to include parsed and structured paper representations, rich metadata and versioning information.
Our work paves the path towards systematic, multi-faceted, evidence-based study of peer review in NLP and beyond.
arXiv Detail & Related papers (2022-11-12T12:29:38Z) - Why Should Adversarial Perturbations be Imperceptible? Rethink the
Research Paradigm in Adversarial NLP [83.66405397421907]
We rethink the research paradigm of textual adversarial samples in security scenarios.
We first collect, process, and release a security datasets collection Advbench.
Next, we propose a simple method based on rules that can easily fulfill the actual adversarial goals to simulate real-world attack methods.
arXiv Detail & Related papers (2022-10-19T15:53:36Z) - Meta Learning for Natural Language Processing: A Survey [88.58260839196019]
Deep learning has been the mainstream technique in natural language processing (NLP) area.
Deep learning requires many labeled data and is less generalizable across domains.
Meta-learning is an arising field in machine learning studying approaches to learn better algorithms.
arXiv Detail & Related papers (2022-05-03T13:58:38Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.